def train_from_file(ifile, file_type): dictionaries = [] sentences = [] with open(ifile, 'r') as fr: sentence_index = 0 sentence = [] nonprojs = [] for line in fr.readlines(): split_line = line.split() if len(split_line) == 10: if file_type == 'conll': word = get_word_from_conll(split_line) if file_type == 'conllu': if split_line[0] == '#': continue word = get_word_from_conllu(split_line) word['deprel'] = 'dep' sentence.append(word) else: if sentence_index >= 0: parser = DependencyParser(sentence) try: log = parser.get_transitions() dictionaries.append(log) sentences.append(sentence) except NonProjectiveParseError as nppe: nonprojs.append((sentence_index, str(nppe))) sentence_index += 1 sentence = [] # break return dictionaries, sentences
def train_from_file(ifile, file_type):
dictionaries = []
sentences = []
with open(ifile, 'r') as fr:
sentence_index = 0
sentence = []
nonprojs = []
for line in fr.readlines():
split_line = line.split()
if len(split_line) == 10:
if file_type == 'conll':
word = get_word_from_conll(split_line)
if file_type == 'conllu':
if split_line[0] == '#':
continue
word = get_word_from_conllu(split_line)
word['deprel'] = 'dep'
sentence.append(word)
else:
if sentence_index >= 0:
parser = DependencyParser(sentence)
try:
log = parser.get_transitions()
dictionaries.append(log)
sentences.append(sentence)
except NonProjectiveParseError as nppe:
nonprojs.append((sentence_index, str(nppe)))
sentence_index += 1
sentence = []
# break
return dictionaries, sentences
def parse_dp(dp_file, wts_file, surp_file, k, ofile, num_sent=None):
parse_stats = {
'correct': 0.0,
'total': 0.0,
'correct_trans_avlbl': 0.0,
'all_correct': 0.0,
'all_correct_total': 0.0,
'correct_label': 0.0,
'sent_correct': 0.0,
'num_sents': 0.0
}
maxent = MaxEnt(wts_file, len(ArcEagerState.transition_types))
with open(dp_file, 'r') as fr:
with open(surp_file, 'w') as fw:
with open(ofile, 'w') as fo:
sentence_index = 0
fw.write('item\troi\tword\tsurprisal\tretrieval\n')
sentence = []
nonprojs = []
for line in fr.readlines() + ['\n']:
split_line = line.split()
if len(split_line) == 10:
word = get_word_from_conll(split_line)
# print word['form'],
sentence.append(word)
else:
if sentence_index % 5 == 0:
print "Sent %s" % sentence_index
if sentence_index >= 0:
parser = DependencyParser(sentence)
parse = parser.best_parse(maxent, k)
for key in parse_stats:
if key in parse:
parse_stats[key] = parse_stats.get(
key, 0) + parse[key]
parse_stats['num_sents'] += 1
parse_stats['sent_correct'] += 1 if (
parse_stats['total'] -
parse_stats['correct'] < 0.5) else 0
for pair in parse['surprisal']:
fw.write(
str(sentence_index + 1) + '\t' +
'\t'.join([str(x) for x in pair]) + '\n')
if len(sentence):
for w in sentence:
w['parent'] = parse['parent'][
w['index']]['index']
fo.write(write_to_conll(w) + '\n')
fo.write('\n')
sentence_index += 1
sentence = []
if num_sent and (sentence_index >= num_sent): break
return parse_stats
def generateCompFiles(model_type, num_iterations, features_cutoff):
if model_type == "basic":
print("Generating Basic Model Competition Predictions")
data = DependencyDataReader(train_file)
basic_features = FullBasicFeatures(data, features_cutoff)
basic_features.initialize_vector()
basic_model = DependencyParser(basic_features, num_iterations)
generateCompTagging(comp_file, basic_model)
elif model_type == "advanced":
print("Generating Advanced Model Competition Predictions")
data = DependencyDataReader(all_file)
advanced_features = AdvancedFeatures(data, features_cutoff)
advanced_features.initialize_vector()
advanced_model = DependencyParser(advanced_features, num_iterations)
generateCompTagging(comp_file, advanced_model)
def parse_dp(dp_file, wts_file, surp_file, k, ofile, num_sent=None):
parse_stats = {'correct': 0.0,
'total': 0.0,
'correct_trans_avlbl': 0.0,
'all_correct': 0.0,
'all_correct_total': 0.0,
'correct_label': 0.0,
'sent_correct': 0.0,
'num_sents': 0.0
}
maxent = MaxEnt(wts_file, len(ArcEagerState.transition_types))
with open(dp_file, 'r') as fr:
with open(surp_file, 'w') as fw:
with open(ofile, 'w') as fo:
sentence_index = 0
fw.write('item\troi\tword\tsurprisal\tretrieval\n')
sentence = []
nonprojs = []
for line in fr.readlines()+['\n']:
split_line = line.split()
if len(split_line) == 10:
word = get_word_from_conll(split_line)
# print word['form'],
sentence.append(word)
else:
if sentence_index % 5 == 0: print "Sent %s"%sentence_index
if sentence_index >= 0:
parser = DependencyParser(sentence)
parse = parser.best_parse(maxent,k)
for key in parse_stats:
if key in parse:
parse_stats[key] = parse_stats.get(key, 0) + parse[key]
parse_stats['num_sents'] += 1
parse_stats['sent_correct'] += 1 if (parse_stats['total'] - parse_stats['correct'] < 0.5) else 0
for pair in parse['surprisal']:
fw.write(str(sentence_index + 1) + '\t' + '\t'.join([str(x) for x in pair]) + '\n')
if len(sentence):
for w in sentence:
w['parent'] = parse['parent'][w['index']]['index']
fo.write(write_to_conll(w)+'\n')
fo.write('\n')
sentence_index += 1
sentence = []
if num_sent and (sentence_index >= num_sent): break
return parse_stats
def main():
global_timer = Timer("Total Runtime")
if len(argv) == 3:
NUM_ITERATIONS = int(argv[1])
FEATURES_CUTOFF = int(argv[2])
elif len(argv) == 2:
NUM_ITERATIONS = int(argv[1])
FEATURES_CUTOFF = 0
else:
NUM_ITERATIONS = 20
FEATURES_CUTOFF = 0
evaluate_per_iteration = False
pretrained_weights = None
time = Timer('Data reader')
train_data = DependencyDataReader(train_file)
time.stop()
print("Number of sentences:", train_data.get_num_sentences())
time = Timer('Advanced Features')
features = AdvancedFeatures(train_data, FEATURES_CUTOFF)
features.initialize_vector()
time.stop()
print("Number of Features:", features.getFeaturesVectorLength())
model = DependencyParser(features, pretrained_weights)
if pretrained_weights is None:
model.fit(NUM_ITERATIONS, evaluate_per_iteration)
results = [
"Number of Iterations: " + str(NUM_ITERATIONS),
"Feature Cutoff: " + str(FEATURES_CUTOFF)
]
model.predict(train_data)
results.append(str(model.evaluate(train_data)))
test_data = DependencyDataReader(test_file)
print("Number of sentences:", test_data.get_num_sentences())
model.predict(test_data)
results.append(str(model.evaluate(test_data)))
global_timer.stop()
